Triple
T15407814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | III-V compound semiconductors |
E368507
|
entity |
| Predicate | typicalGroupVElement |
P2776
|
FINISHED |
| Object | arsenic |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: arsenic | Statement: [III-V compound semiconductors, typicalGroupVElement, arsenic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalGroupVElement Context triple: [III-V compound semiconductors, typicalGroupVElement, arsenic]
-
A.
typicalGroup
Indicates that the subject belongs to or represents a standard, characteristic, or commonly occurring group associated with the object.
-
B.
typicalComponent
Indicates that one entity is a standard or representative component or part of another entity.
-
C.
typicalEntryType
Indicates the usual or standard category or kind of entry associated with something.
-
D.
typicalMembers
chosen
Indicates that the related entities are representative or characteristic members of a larger group, category, or class.
-
E.
describedGroup
Indicates that an entity provides a description or characterization of a particular group or collection of entities.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d85a16c68c819099c1b547fbc87b32 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03ea36c6881909eaea48e9608897a |
completed | April 16, 2026, 1:42 a.m. |
| PD | Predicate disambiguation | batch_69ded27b8cac8190bfa77698d53c5d1c |
completed | April 14, 2026, 11:49 p.m. |
Created at: April 10, 2026, 3:20 a.m.